agentic-commerce-catalog

create_music

AI music generation from a text prompt. Creates a complete original song with vocals, melody, and full arrangement as a finished MP3, not a loop or preview. Describe genre, mood, instrumentation, and tempo, supply your own lyrics, request an instrumental, or pin a style tag. Use for soundtracks under video, release-ready artist tracks, podcast and game themes, and demo sketches. Async: poll songId until model_version leaves 'pending'. — $0.50 USDC via x402 on Base (chain 8453).

Input Schema

TableJSON Schema

Name	Required	Description
`tags`	No	Comma-separated keywords to tag the generated file.
`style`	No	Specific musical style or genre tag (e.g., 'Hip Hop', 'Ambient', 'Rock'). Helping the AI focus on a specific sound.
`lyrics`	No	Your custom lyrics. Required if custom_mode is true.
`prompt`	Yes	Describe the song you want to create. Include genre, mood, instruments, and any specific vibe. Example: 'Upbeat 80s synthwave with driving bass and neon atmosphere' or 'A melancholic acoustic guitar ballad about rain'.
`custom_mode`	No	Set to true to use your own lyrics provided in the 'lyrics' field.
`vocal_gender`	No	Preferred gender for the vocalist ('m' for male, 'f' for female).
`durationSeconds`	No	Duration of the track in seconds. Defaults to a full-length song.
`make_instrumental`	No	If true, generates a track without vocals.

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full disclosure burden and does so well: it states the output format, async polling behavior (songId/model_version leaving 'pending'), and pricing/payment rails (USDC via x402 on Base). This goes well beyond the schema's field-level information.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and every sentence carries weight—use cases, async behavior, and cost are all relevant. The first two sentences overlap slightly in saying this is text-prompt music generation, which keeps it just shy of a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description provides the necessary extra context: final MP3 output, async polling touchpoints, and payment details. It is terse about the actual poll mechanism and response shape, but the 100% input-schema coverage compensates for parameter-side gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already documents all 8 parameters, so the baseline is 3; the description adds useful mapping like 'Describe genre, mood, instrumentation, and tempo' (prompt), 'supply your own lyrics' (custom_mode/lyrics), 'request an instrumental' (make_instrumental), and 'pin a style tag' (style). This enriches without duplicating schema detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a specific verb and resource: AI music generation from a text prompt producing a complete original song as an MP3. It also differentiates from the sibling media tools by specifying vocals, melody, full arrangement, and 'not a loop or preview'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete, relevant use cases (soundtracks, release-ready tracks, podcast/game themes, demo sketches) and clarifies the output type. It does not explicitly name sibling alternatives or state when not to use this tool, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All agentic-commerce-catalog tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

Each tool targets a distinctly different media type: image, video, and music. There is no overlap or ambiguity between generating a still image, a video clip, or an original song.

Naming Consistency3/5

Two tools follow the agent_ prefix pattern (agent_image, agent_video) while the third uses create_music, mixing conventions. The names are still readable, but the pattern is not fully consistent.

Tool Count4/5

Three tools is a lean but reasonable set for a media generation server. Each tool covers a meaningful content type and earns its place, though the server could arguably include additional related creation tools.

Completeness4/5

The surface covers the core generation needs for image, video, and music content. Minor gaps exist, such as no editing or asset management tools, but the core lifecycle of generating and receiving media is complete.

Resources

Need Help?